Shapley Value Based Multi-Agent Reinforcement Learning: Theory, Method and Its Application to Energy Network

arXiv:2402.15324v1 Announce Type: cross
Abstract: Multi-agent reinforcement learning is an area of rapid advancement in artificial intelligence and machine learning. One of the important questions to be answered is how to conduct credit assignment in a multi-agent system. There have been many schemes designed to conduct credit assignment by multi-agent reinforcement learning algorithms. Although these credit assignment schemes have been proved useful in improving the performance of multi-agent reinforcement learning, most of them are designed heuristically without a rigorous theoretic …

abstract advancement agent application artificial artificial intelligence arxiv credit cs.lg cs.ma energy intelligence machine machine learning multi-agent network questions reinforcement reinforcement learning theory type value